Paper Citation Record · LEDGER

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference

As of 9 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 3 inbound Pith citation observations for arXiv:2511.04805.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2511.04805 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T23:41:52.952675Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:51:34.294269Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-06-29T12:43:25.643835Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 01d8d632-0f50-416c-a227-1bb7d1a31f30 · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.834106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08b778f4-0e17-4462-a0bc-d74535b28087 · outbound

This paper cites Retraining-free merging of sparse moe via hierarchical clustering, 2025.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Retraining-free merging of sparse moe via hierarchical clustering, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.837795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 991a0df8-9dd3-4937-bcc5-32c20e3974ef · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.840823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 045acc1c-6900-406b-a9f8-8b148b8ae78c · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.843975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90d95ac3-731f-4fa0-908f-8216daf7813a · outbound

This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.847092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1e71420-08dd-4415-bec4-d6d31c269da7 · outbound

This paper cites MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.850528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d306b013-b76d-4eef-89b4-564c7cad30cc · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.853842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a02cae48-d646-42a7-943f-7854944a495e · outbound

This paper cites Delta Decompression for MoE-based LLMs Compression.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Delta Decompression for MoE-based LLMs Compression

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.856931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00087d0a-f498-4b2b-8434-ae3b5b9bc33d · outbound

This paper cites Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.860011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f8a18a1-2ca8-4822-a646-55e5456bf810 · outbound

This paper cites Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.862989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6576e63a-5b29-4b7a-b325-5a756d272590 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Measuring Massive Multitask Language Understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.865923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a063dfd-ee8a-45a6-869c-13db3188df59 · outbound

This paper cites MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.868779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee6e218f-ac0d-4a91-ad32-5c40fc7a4fff · outbound

This paper cites MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.871652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ca93892-cceb-4536-a2cb-23743e9981af · outbound

This paper cites Mixtral of Experts.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Mixtral of Experts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.874759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5345532e-07ac-4710-acc3-c0145d49c1b6 · outbound

This paper cites SqueezeLLM: Dense-and-Sparse Quantization.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference SqueezeLLM: Dense-and-Sparse Quantization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.877669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f19fcee-eeb6-46a2-9a2f-59a5a0f17840 · outbound

This paper cites Compressed sparse tiles for memory-efficient unstructured and semi-structured sparsity.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Compressed sparse tiles for memory-efficient unstructured and semi-structured sparsity

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.880459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8d09d90-56db-404f-952d-062cf6df0437 · outbound

This paper cites an unresolved cited work.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.883263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a99e4a-4446-4a66-978b-cd849d8a7891 · outbound

This paper cites STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.885793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa53dd31-ba35-43bd-a312-d9718e0365cf · outbound

This paper cites Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.889236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d48c4271-7f56-4a8e-b8f5-47e105aec39a · outbound

This paper cites Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.892552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5df031a-ec70-4ec2-b6c7-fb95b160fc42 · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.895649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cd25960-a6da-476c-8de5-adbda4992407 · outbound

This paper cites Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.898841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da4f4a16-d4d7-4b78-845a-cd58e8b87437 · outbound

This paper cites Pointer sentinel mixture models, 2016.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Pointer sentinel mixture models, 2016

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.902228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 025e935a-b34d-42c3-8a2b-1a75f9a5c104 · outbound

This paper cites Ronald Miller.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Ronald Miller

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.905552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe2b623-33f9-4e78-96a5-feb718932f01 · outbound

This paper cites Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.908779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acdb41fb-8c1e-448f-beb2-a547391a88cb · outbound

This paper cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.911960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a676dbe-75d5-4327-b584-e9c86751f416 · outbound

This paper cites Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.915255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b98c728-1004-4379-a87a-1534c1aad3cb · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference A Simple and Effective Pruning Approach for Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.918257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b123788-4dea-4741-9699-a2a1fcd7b1fb · outbound

This paper cites Qwen1.5-moe: Matching 7b model performance with 1/3 activated parameters", February 2024.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Qwen1.5-moe: Matching 7b model performance with 1/3 activated parameters", February 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.921149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 011be3d4-145b-4233-99e7-dfedbfc066f5 · outbound

This paper cites Qwen3 Technical Report.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Qwen3 Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.924296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c986254d-4e84-45a7-81e5-e58639686ea9 · outbound

This paper cites MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.927468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 926af6f5-b454-492f-bdc7-4c4613c6064b · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.930376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021d6ffe-eb1a-4971-a46c-8aa30a6331d9 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.933402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c332b9a1-ca43-443a-bc6a-f37421567945 · outbound

This paper cites 70 URL https://arxiv.org/abs/2504.11651.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference 70 URL https://arxiv.org/abs/2504.11651

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.936512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35a97476-723d-43b8-bf54-07c85b7fceb1 · outbound

This paper cites Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.939720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3de22f6b-4fb0-432a-9842-f726d01d94dd · outbound

This paper cites write newline.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference write newline

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.942847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3cbb099-45b1-45f8-a50e-aff714f8f1d8 · outbound

This paper cites @esa (Ref.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference @esa (Ref

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.946582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ece3df0-42ae-408b-bd84-f23684b18c69 · outbound

This paper cites an unresolved cited work.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.949651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c352232-09da-40ee-a84f-2162e5063b0b · outbound

This paper cites However, their widespread deployment remains limited due to the high memory overhead associated with storing all expert parameters, particularly as the number of experts increases.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference However, their widespread deployment remains limited due to the high memory overhead associated with storing all expert parameters, particularly as the number of experts increases

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.952675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 35e6eba3-7f8f-4c47-9480-71d5faa9e20b · inbound

ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits cites this paper.

ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T09:32:55.640537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 046135be-7fb7-4b0c-bec4-6263e30c6054 · inbound

Pruning and Distilling Mixture-of-Experts into Dense Language Models cites this paper.

Pruning and Distilling Mixture-of-Experts into Dense Language Models PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-07T04:17:56.460609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 98ebed38-9329-46d0-b19d-3d444bf03a0f · inbound

Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models cites this paper.

Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T23:51:34.294269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.